Estimate — sign in for exact rates.

 Trusted GPU & AI infrastructure since 2015 — Huntsville, AL
AMD Inference

FastLLM Preview 2026.11.12.2 test results

Bitworks’ own tests of this release on 3 AMD Radeon PCs, tested 2026-11-15. Stable release (Preview label): not a qualified release; recipes remain candidates.

  • Release checks: 14 passed
  • Automated tests: 8/8 passed
  • Window checklist: 35 pass

Release checks

Pass 14 checks on the release. Covers: SHA256SUMS, installer and package signatures, signed file catalog, installed tree equals package, uninstall keeps data.

Installer: FastLLM-Setup-2026.11.12.2.exe
SHA-256 08f37c9cce1421700f34f34a63c16045531762d582390d2591b9afdbf005b7b3

Release page on GitHub

Test hardware

  • AMD Radeon RX 7900 XT 20GB — Resizable BAR on
  • AMD Radeon RX 7900 XTX 24GB — Resizable BAR on
  • AMD Radeon RX 7600 XT 16GB — Resizable BAR not recorded

Automated tests

Check Result Cards Account
Update from 2026.10.21.12 to 2026.11.12.2 over the stable channel with FastLLM's own updater
SHA256SUMS, installer size, hash, Bitworks signature and version verified; installed files match the signed catalog. Releases: 2026.11.12.2.
Pass XT, XTX standard Windows user
Default start picks the HIP setup, no fallback, self-test passes
Releases: 2026.11.12.2.
Pass XT, XTX standard Windows user
Vulkan setup starts when chosen, self-test passes
Releases: 2026.11.12.2.
Pass XT, XTX standard Windows user
Update in place from an existing 2026.10.21.12 installation (canary channel) with FastLLM's own updater
Installed, files match the signed catalog, same folder, no old files left behind. The card is not involved. Releases: 2026.11.12.1.
Pass lab PC standard Windows user
Thinking Off on the HIP and the Vulkan setup
The server starts with thinking off and the self-test passes. Releases: 2026.11.12.1.
Pass XTX standard Windows user
Local chat page on (HIP)
Served only on the local address (only this PC can reach it), with no built-in tools; off by default (the default start serves no page). Releases: 2026.11.12.1.
Pass XTX standard Windows user
A different local port (18181, HIP)
Served only on the local address at that port (only this PC can reach it); nothing on 8080. Releases: 2026.11.12.1.
Pass XTX standard Windows user
Run log holds no prompts or answers; nothing downloaded during starts; settings untouched
Releases: 2026.11.12.1.
Pass XTX standard Windows user

Self-test speed

Workload: 1 discarded warm-up + 2 measured runs; 512-token prompt; 128 generated tokens; server timings (median)

Card Setup Generation (tok/s) Prompt (tok/s) First token
AMD Radeon RX 7900 XT 20GB HIP (the setup FastLLM picks) 33.0 777.2 660 ms
AMD Radeon RX 7900 XT 20GB Vulkan (fallback) 32.9 579.8 885 ms
AMD Radeon RX 7900 XTX 24GB HIP (the setup FastLLM picks) 32.8 869.8 591 ms
AMD Radeon RX 7900 XTX 24GB Vulkan (fallback) 36.3 665.6 771 ms

HIP processes the prompt faster and starts answering sooner on both cards. On the RX 7900 XTX, Vulkan generates faster (36.3 against 32.83 tok/s); on the RX 7900 XT, HIP and Vulkan generate at about the same speed.

Window checklist

Real FastLLM window by remote desktop. Lines 1 to 43: the RX 7900 XTX PC (administrator account, User Account Control on, FastLLM not elevated) and the RX 7900 XT PC (standard account; lines 3, 6, 8, 10 to 13, 16 on 2026.10.15.12; 3, 12, 13, 16 to 19 on 2026.10.15.13). Resizable BAR values are for this release's boards; lines 9 and 14 used an earlier RX 7900 XTX board with it off.

“Ran on” lists the releases each line was run on. A line not re-run on 2026.11.12.2 keeps the earlier release it passed on.

Line Check Result Notes Ran on
1 Download the signed installer from the release page and install it Pass No admin prompt. Edge may hold the file as not commonly downloaded; Keep releases it. Publisher shown as Bitworks LLC. 2026.10.15.9, 2026.10.15.11
3 Open FastLLM Pass Title and notice correct; no integrity warning. Also passed with a standard Windows account on the RX 7900 XT. 2026.10.15.9 to .13
6 Plan names the best setup for the card Pass "Measured by Bitworks on this card" with a See results link. Also passed with a standard Windows account on the RX 7900 XT. 2026.10.15.9, 2026.10.15.12
7 Model license shown before any download Pass Exact model, revision, license and size reviewed before a 15.33 GiB download; download verified. 2026.10.15.9
8 Self-test after the server is ready Pass Self-test line with generation and prompt speed. Also passed with a standard Windows account on the RX 7900 XT. 2026.10.15.9 to .12
9 Resizable BAR off is detected and handled Pass Note with a How to turn it on link on the PC with Resizable BAR off. 2026.10.15.9
10 Closing the window keeps a background server running Pass Background mode keeps serving; a foreground run asks before stopping. Also passed with a standard Windows account on the RX 7900 XT. 2026.10.15.9, 2026.10.15.12
11 Reopening reattaches to the running server Pass Attach running names the engine: Running on HIP (AMD ROCm 10.0). Also passed with a standard Windows account on the RX 7900 XT. 2026.10.15.9, 2026.10.15.11, 2026.10.15.12
12 Sign out and back in Pass Standard Windows account, RX 7900 XT, background run attached. Signing out ended it, as documented (background mode runs only while signed in). After signing back in, FastLLM said the last background run ended without Stop; nothing was stuck and a new background start worked. On 2026.10.15.12 a background-ownership notice briefly showed after that start; 2026.10.15.13 fixes it. 2026.10.15.12, 2026.10.15.13
13 Stop Pass Foreground and background stop; after a background stop the window says Stopped. The background run ended. Also passed with a standard Windows account on the RX 7900 XT. 2026.10.15.11, 2026.10.15.12, 2026.10.15.13
14 Resizable BAR setting persists Pass — 2026.10.15.9
15 Uninstall offers to keep models and engines Pass Default No keeps them; the offer shows the real size (18,023 MB) and covers engine components. 2026.10.15.11
16 Layout Pass Long status lines end with an ellipsis and show the full text on hover. Also passed with a standard Windows account on the RX 7900 XT. 2026.10.15.11, 2026.10.15.12, 2026.10.15.13
17 Update banner for a newer release Pass FastLLM 2026.10.15.13 is available, with Release notes and Update (standard Windows account). 2026.10.15.11 to .12, 2026.10.15.12 to .13
18 Update from the window Pass Downloads, checks the Bitworks signature, runs the installer: FastLLM was updated to 2026.10.15.13 (standard Windows account). 2026.10.15.11 to .12, 2026.10.15.12 to .13
19 Reopen after the update Pass New version; no banner, no integrity warning. 2026.10.15.12, 2026.10.15.13
20 Check for updates setting persists Pass — 2026.10.15.9
21 Experimental community components switch Pass Explains experimental recipes; off by default. 2026.10.15.9
22/32 Engine components list and removal Pass Sizes shown; the runtime cannot be removed while the engine needs it. 2026.10.15.9, 2026.10.15.12
23/24 Choose another setup Pass Two setups for the card, both measured by Bitworks: Vulkan (built in) and HIP. 2026.10.15.9
27 Engine component consent window Pass Each component with its source and license links; nothing installs until every box is ticked. Names the model (Qwen3.8-27B UD-Q4_K_M). Wording and flow reviewed and approved by the Bitworks owner. 2026.10.15.9, 2026.10.15.12
28 License links Pass Each license link opens the right page: the GitHub license pages for llama.cpp b11658 and for the ROCm interop library at its pinned commit, and the AMD HIP SDK license page. Reviewed and approved by the Bitworks owner. 2026.10.15.9, 2026.10.15.12
35/36 No consent: FastLLM says so and starts Vulkan Pass Running on Vulkan (fallback: AMD license not accepted). 2026.10.15.9
37 A declined license is remembered Pass — 2026.10.15.9
38 HIP from Choose another setup Pass Components download and are verified; Running on HIP (AMD ROCm 10.0). 2026.10.15.9, 2026.10.15.12
39/40/41 Install engine components automatically (opt-in) Pass Confirmation with the license links; on: installs without asking; off: stays off. 2026.10.15.9
42 Background run names its engine Pass — 2026.10.15.9
43 Component install failure Pass The network could not be switched off on a remotely operated PC, so the install failure was forced locally (the components' staging folder was blocked). FastLLM said the engine components could not be installed, continued on Vulkan (Running on Vulkan (fallback: HIP components could not be installed)), and asked for consent again on the next start. 2026.10.15.12
44 Settings: port, Thinking, local chat page Pass Defaults shown (port 8080, local address only; Thinking Auto; chat page off). Changes are saved and applied: the next run listened only on the local address at the new port. Known issue: the Thinking box hides the start of the selected text; the value is applied correctly. On the RX 7600 XT PC (standard account, Vulkan), with the lab build made from the same source as this release. 2026.11.09.1
45 Connect an app Pass Base URL, Anthropic base URL, model name and context limit, each with Copy; /v1/responses labelled partial at this engine version; settings cards for the listed apps. On the RX 7600 XT PC (standard account, Vulkan), with the lab build made from the same source as this release. 2026.11.09.1
46 Check the API formats Pass Chat, messages and responses each passed; the window says nothing is kept. On the RX 7600 XT PC (standard account, Vulkan), with the lab build made from the same source as this release. 2026.11.09.1
47 Open chat, foreground and background run Pass The local chat page opened in the browser on the local address for both. No message was sent. On the RX 7600 XT PC (standard account, Vulkan), with the lab build made from the same source as this release. 2026.11.09.1
48 Downloaded models Pass Models listed with their sizes and the free disk space. (Remove was not clicked.) On the RX 7600 XT PC (standard account, Vulkan), with the lab build made from the same source as this release. 2026.11.09.1
49 Save support bundle Pass Lists what it will contain, replaces items that identify the PC or user with placeholders, writes one zip to the chosen place; nothing is uploaded. On the RX 7600 XT PC (standard account, Vulkan), with the lab build made from the same source as this release. 2026.11.09.1
50 Open logs Pass Opens the folder with the run's log. On the RX 7600 XT PC (standard account, Vulkan), with the lab build made from the same source as this release. 2026.11.09.1

Earlier engine tests

These tests ran on earlier FastLLM releases. They are kept for the record and describe the release named on each test, not the current download.

Tested with FastLLM 2026.10.15.13

Engine check

llama.cpp b11712 Windows Vulkan x64

Tested 2026-10-17 with FastLLM 2026.10.15.13. At that release: Bitworks lab comparison, not a FastLLM release; FastLLM still ships b10698 for Vulkan.

Method: Same model file, context, server arguments and environment as FastLLM's Vulkan setup for each card; arms in order shipped, candidate, shipped (drift control); FastLLM's own self-test (1 discarded warm-up + 2 measured runs; 512-token prompt; 128 generated tokens; server timings, median) plus a fixed correctness probe; standard Windows user.

Card Run Engine Generation (tok/s) Prompt (tok/s) First token Layers on GPU Self-test Correctness
AMD Radeon RX 7900 XT 20GB Shipped, first run llama.cpp b10698 Vulkan 34.1 538.3 954 ms 66/66 Pass Pass
AMD Radeon RX 7900 XT 20GB Candidate llama.cpp b11712 Vulkan 36.5 607.2 847 ms 66/66 Pass Pass
AMD Radeon RX 7900 XT 20GB Shipped, second run llama.cpp b10698 Vulkan 33.6 539.1 951 ms 66/66 Pass Pass
AMD Radeon RX 7900 XTX 24GB Shipped, first run llama.cpp b10698 Vulkan 33.6 658.1 781 ms 66/66 Pass Pass
AMD Radeon RX 7900 XTX 24GB Candidate llama.cpp b11712 Vulkan 34.5 682.2 752 ms 66/66 Pass Pass
AMD Radeon RX 7900 XTX 24GB Shipped, second run llama.cpp b10698 Vulkan 34.5 671.9 763 ms 66/66 Pass Pass
Card Generation vs shipped Prompt vs shipped Shipped-run drift (generation / prompt)
AMD Radeon RX 7900 XT 20GB +7.9% +12.7% 1.4% / 0.2%
AMD Radeon RX 7900 XTX 24GB +1.4% +2.5% 2.6% / 2.1%

Keep b10698 for now. The rule declared before the run needed a clear win on both cards: the RX 7900 XT improved clearly; the RX 7900 XTX did not regress but its gain is within run-to-run variation.

llama.cpp b11712 release on GitHub
SHA-256 7b80950ca99093f5a7b6d9ce2e2d52c5fa650f5fd3a583b1ad000dbd38ce6085

Adoption test

llama.cpp b11712 Windows Vulkan x64

Tested 2026-10-19 with FastLLM 2026.10.15.13. At that release: Bitworks lab test, not a FastLLM release; FastLLM still ships b10698 for Vulkan.

Method: Retest of the 2026-10-17 adoption test with heat controlled: five minutes idle before the first run and two minutes idle before every run. Same model file, context, server arguments and environment as FastLLM's Vulkan setup; runs interleaved shipped/candidate four times per card; FastLLM's own self-test on every run; on the first pair, FastLLM's API canary, its 3-case semantic smoke and its 24-case task-quality suite; standard Windows user. The rule is the same as on 2026-10-17.

Rule: Adopt only if every run passes, quality is not lower, no card is slower on average, and at least one card is clearly faster than every baseline run.

Thresholds checked by Bitworks: “no slower” means the candidate’s average is at least 98% of the shipped average for both generation and prompt; “clearly faster” means every candidate run beats every shipped run by at least 3% at generation, or by at least 5% at prompt processing.

Card Run Engine Generation (tok/s) Prompt (tok/s) First token Layers on GPU Self-test Correctness
AMD Radeon RX 7900 XT 20GB Shipped, run 1 llama.cpp b10698 Vulkan 33.9 545.1 941 ms 66/66 Pass Pass
AMD Radeon RX 7900 XT 20GB Candidate, run 1 llama.cpp b11712 Vulkan 35.2 589.1 873 ms 66/66 Pass Pass
AMD Radeon RX 7900 XT 20GB Shipped, run 2 llama.cpp b10698 Vulkan 34.3 543.1 946 ms 66/66 Pass Pass
AMD Radeon RX 7900 XT 20GB Candidate, run 2 llama.cpp b11712 Vulkan 34.8 586.0 877 ms 66/66 Pass Pass
AMD Radeon RX 7900 XT 20GB Shipped, run 3 llama.cpp b10698 Vulkan 32.4 533.6 961 ms 66/66 Pass Pass
AMD Radeon RX 7900 XT 20GB Candidate, run 3 llama.cpp b11712 Vulkan 35.3 602.0 854 ms 66/66 Pass Pass
AMD Radeon RX 7900 XT 20GB Shipped, run 4 llama.cpp b10698 Vulkan 34.0 526.0 975 ms 66/66 Pass Pass
AMD Radeon RX 7900 XT 20GB Candidate, run 4 llama.cpp b11712 Vulkan 35.1 568.7 902 ms 66/66 Pass Pass
AMD Radeon RX 7900 XTX 24GB Shipped, run 1 llama.cpp b10698 Vulkan 34.7 651.1 788 ms 66/66 Pass Pass
AMD Radeon RX 7900 XTX 24GB Candidate, run 1 llama.cpp b11712 Vulkan 35.7 696.1 738 ms 66/66 Pass Pass
AMD Radeon RX 7900 XTX 24GB Shipped, run 2 llama.cpp b10698 Vulkan 35.8 648.7 791 ms 66/66 Pass Pass
AMD Radeon RX 7900 XTX 24GB Candidate, run 2 llama.cpp b11712 Vulkan 34.7 697.8 735 ms 66/66 Pass Pass
AMD Radeon RX 7900 XTX 24GB Shipped, run 3 llama.cpp b10698 Vulkan 34.1 669.0 767 ms 66/66 Pass Pass
AMD Radeon RX 7900 XTX 24GB Candidate, run 3 llama.cpp b11712 Vulkan 35.0 699.4 734 ms 66/66 Pass Pass
AMD Radeon RX 7900 XTX 24GB Shipped, run 4 llama.cpp b10698 Vulkan 34.2 650.6 788 ms 66/66 Pass Pass
AMD Radeon RX 7900 XTX 24GB Candidate, run 4 llama.cpp b11712 Vulkan 34.6 694.5 739 ms 66/66 Pass Pass
Card Check Shipped (b10698) Candidate (b11712)
AMD Radeon RX 7900 XT 20GB API canary Pass Pass
AMD Radeon RX 7900 XT 20GB Semantic smoke 2/3 2/3
AMD Radeon RX 7900 XT 20GB Task quality 21/24 21/24
AMD Radeon RX 7900 XTX 24GB API canary Pass Pass
AMD Radeon RX 7900 XTX 24GB Semantic smoke 2/3 2/3
AMD Radeon RX 7900 XTX 24GB Task quality 21/24 21/24
Card Mean generation vs shipped Mean prompt vs shipped No slower Clearly faster than every shipped run
AMD Radeon RX 7900 XT 20GB +4.3% +9.2% Yes No
AMD Radeon RX 7900 XTX 24GB +0.8% +6.4% Yes No

Not adopted: FastLLM keeps b10698. With cool-downs between runs, quality was identical and no card was slower; b11712 was faster in every pair on the RX 7900 XT, and at prompt processing in every pair on the RX 7900 XTX, but not by the margin over every baseline run that the rule requires.

llama.cpp b11712 release on GitHub
SHA-256 7b80950ca99093f5a7b6d9ce2e2d52c5fa650f5fd3a583b1ad000dbd38ce6085

Earlier run: llama.cpp b11712 Windows Vulkan x64

An earlier run of the same adoption test; the newer run is above.

Tested 2026-10-17 with FastLLM 2026.10.15.13. At that release: Bitworks lab test, not a FastLLM release; FastLLM still ships b10698 for Vulkan.

Method: Follow-up to the engine check, aimed at adoption. Same model file, context, server arguments and environment as FastLLM's Vulkan setup; runs interleaved shipped/candidate three times per card; FastLLM's own self-test on every run; on the first pair, FastLLM's API canary, its 3-case semantic smoke and its 24-case task-quality suite; standard Windows user.

Rule: Adopt only if every run passes, quality is not lower, no card is slower on average, and at least one card is clearly faster than every baseline run.

Thresholds checked by Bitworks: “no slower” means the candidate’s average is at least 98% of the shipped average for both generation and prompt; “clearly faster” means every candidate run beats every shipped run by at least 3% at generation, or by at least 5% at prompt processing.

Card Run Engine Generation (tok/s) Prompt (tok/s) First token Layers on GPU Self-test Correctness
AMD Radeon RX 7900 XT 20GB Shipped, run 1 llama.cpp b10698 Vulkan 34.3 538.7 952 ms 66/66 Pass Pass
AMD Radeon RX 7900 XT 20GB Candidate, run 1 llama.cpp b11712 Vulkan 34.5 592.7 868 ms 66/66 Pass Pass
AMD Radeon RX 7900 XT 20GB Shipped, run 2 llama.cpp b10698 Vulkan 33.0 522.4 983 ms 66/66 Pass Pass
AMD Radeon RX 7900 XT 20GB Candidate, run 2 llama.cpp b11712 Vulkan 34.0 582.9 879 ms 66/66 Pass Pass
AMD Radeon RX 7900 XT 20GB Shipped, run 3 llama.cpp b10698 Vulkan 32.2 511.3 1,004 ms 66/66 Pass Pass
AMD Radeon RX 7900 XT 20GB Candidate, run 3 llama.cpp b11712 Vulkan 34.8 550.9 932 ms 66/66 Pass Pass
AMD Radeon RX 7900 XTX 24GB Shipped, run 1 llama.cpp b10698 Vulkan 34.1 642.0 800 ms 66/66 Pass Pass
AMD Radeon RX 7900 XTX 24GB Candidate, run 1 llama.cpp b11712 Vulkan 33.7 664.7 773 ms 66/66 Pass Pass
AMD Radeon RX 7900 XTX 24GB Shipped, run 2 llama.cpp b10698 Vulkan 34.3 670.2 767 ms 66/66 Pass Pass
AMD Radeon RX 7900 XTX 24GB Candidate, run 2 llama.cpp b11712 Vulkan 35.2 701.2 732 ms 66/66 Pass Pass
AMD Radeon RX 7900 XTX 24GB Shipped, run 3 llama.cpp b10698 Vulkan 32.9 659.9 778 ms 66/66 Pass Pass
AMD Radeon RX 7900 XTX 24GB Candidate, run 3 llama.cpp b11712 Vulkan 34.2 687.9 745 ms 66/66 Pass Pass
Card Check Shipped (b10698) Candidate (b11712)
AMD Radeon RX 7900 XT 20GB API canary Pass Pass
AMD Radeon RX 7900 XT 20GB Semantic smoke 2/3 2/3
AMD Radeon RX 7900 XT 20GB Task quality 21/24 21/24
AMD Radeon RX 7900 XTX 24GB API canary Pass Pass
AMD Radeon RX 7900 XTX 24GB Semantic smoke 2/3 2/3
AMD Radeon RX 7900 XTX 24GB Task quality 21/24 21/24
Card Mean generation vs shipped Mean prompt vs shipped No slower Clearly faster than every shipped run
AMD Radeon RX 7900 XT 20GB +3.8% +9.8% Yes No
AMD Radeon RX 7900 XTX 24GB +1.7% +4.1% Yes No

Not adopted: FastLLM keeps b10698. Quality was identical and no card was slower; b11712 was faster on average on both cards, but not beyond the spread of the baseline runs, which the rule required.

llama.cpp b11712 release on GitHub
SHA-256 7b80950ca99093f5a7b6d9ce2e2d52c5fa650f5fd3a583b1ad000dbd38ce6085