loom-fun/bartowski-Qwen2.5-0.5B-Instruct-loom

Qwen2.5-0.5B-Instruct (Q4_K_M) for AMD Loom

A Loom package (.loom programs and a model.json card) for the unmodified GGUF checkpoint bartowski/Qwen2.5-0.5B-Instruct-GGUF (Qwen2.5-0.5B-Instruct-Q4_K_M.gguf), generated on an AMD Ryzen AI Max+ 395 "Strix Halo" with the loom-skills workflow.

Quick start

pip install "hrx-loom[hf]"
loom-fetch https://huggingface.co/loom-fun/bartowski-Qwen2.5-0.5B-Instruct-loom/resolve/main/model.json --materialize=copy --output=Qwen2.5-0.5B-Instruct
loom-serve --model=Qwen2.5-0.5B-Instruct/model.json --device=amdgpu --memory_bytes=5000000000

The server listens on 127.0.0.1:8080 and answers OpenAI-style /v1/chat/completions requests.

Performance vs llama.cpp

metric	llama.cpp	Loom	margin	roofline	Loom % of roofline	DevLab llama.cpp	DevLab Loom	DevLab llama.cpp Vulkan	local ÷ DevLab (llama.cpp, Loom)
decode tok/s, short prompt	285.6	327.1	+15 %	675.8	48 %	263.0	319.5 ¹	383.9	1.09, 1.02
decode tok/s, 2k context	254.2	430.8	+69 %	1176.4	37 %	283.5	453.0 ¹	299.1	0.90, 0.95
decode tok/s, 32k context	228.0	287.2	+26 %	728.0	39 %	153.4	258.2 ¹	201.4	1.49, 1.11
prefill tok/s, 1k document	10835.2	17118.7	+58 %	77768.6	22 %	11540.3	17183.0 ¹	12872.1	0.94, 1.00
prefill tok/s, 2k document	9541.7	17627.0	+85 %	73596.4	24 %	10467.0	18116.4 ¹	12778.9	0.91, 0.97
prefill tok/s, 8k document	8109.9	15667.4	+93 %	55675.2	28 %	5749.8	15420.6 ¹	9014.2	1.41, 1.02
prefill tok/s, 16k document	5519.2	11906.1	+116 %	42029.3	28 %	4091.9	12009.3 ¹	6208.4	1.35, 0.99
prefill tok/s, 32k document	3852.2	7929.1	+106 %	28203.9	28 %	3162.2	7989.4 ¹	3718.2	1.22, 0.99
4 streams, aggregate decode tok/s	746.1	678.1	-9 %	2751.8	25 %	822.1	606.2 ¹	964.5	0.91, 1.12
speculative decoding, drafted tokens accepted	—	12 % ²	—	n/a	n/a	n/a	n/a	n/a	n/a

• llama.cpp: build llamacpp-rocm/b1369, server arguments -ngl 99 -cram 0 --spec-type ngram-simple -c 33792 -kvu -np 4.
• Loom: speculative decoding on (n-gram prompt lookup, depth 2).
• Same GGUF on both engines, tokens per second. Loom: client-side timing; llama.cpp: server-side timings. Runs per value: decode and prefill 2 (mean), 4 streams 3 (median).
• Measured 2026-11-08; device AMD RYZEN AI MAX+ 395 w/ Radeon 8060S, AMD Radeon 8060S Graphics, Ubuntu 26.04; hrx-loom 0.1.0 (hrx-system d01d1c1); source: local run.
• ¹ Measured 2026-11-08; device not recorded; hrx-loom unknown; source: DevLab Dispatch run 42527799430.
• ² Measured 2026-11-08; device AMD RYZEN AI MAX+ 395 w/ Radeon 8060S, AMD Radeon 8060S Graphics, Ubuntu 24.04; hrx-loom 0.1.0 (hrx-system d01d1c1); source: DevLab Dispatch run 42527979776.
• DevLab: the same measurement on an AMD DevLab Dispatch Strix Halo runner; local ÷ DevLab is the local value over the DevLab value of each engine, recorded for comparison, not a verdict.
• DevLab llama.cpp Vulkan: build llamacpp-vulkan/b12211 (archive sha256 9759acd), server arguments -ngl 99 -cram 0 --spec-type ngram-simple -c 147456 -np 4; same GGUF, prompts and settings as llama.cpp; measured 2026-11-09 in its own DevLab job (a different runner than the other DevLab columns: compare the engines through ratios, not across jobs); source: DevLab Dispatch run 42569157613. Differs from llama.cpp: KV cache: 4 per-slot caches (-np 4, -c 147456, no -kvu) instead of the ROCm baseline's unified pool: b12211's Vulkan backend has no GPU kernel for the fused flash attention over K/V rows that the unified pool uses.
• Drafted tokens accepted: the share of the drafter's proposed tokens the model accepted during the spec gate's requests.
• Roofline: the hardware ceiling for this GGUF on AMD Ryzen AI Max+ 395 "Strix Halo" (gfx1151) at 216 GB/s and 59 TFLOP/s, from loom-roofline roofline.py (loom-skills ecb661b); decode and 4 streams with speculative decoding: verify passes × (1 + acceptance × depth 2) tokens per pass, the drafter's cost not counted; acceptance measured in the row's own session: decode 11 %, decode at 2k 63 %, decode at 32k 82 %, 4 streams 17 %.
• — not measured; n/a not applicable.

Features

feature	status	detail
API	✅	OpenAI-style /v1/chat/completions
tool calling	✅	OpenAI-style tools and tool_calls
reasoning / thinking	—	not applicable
reasoning effort	—	not applicable
speculative decoding	✅	n-gram prompt lookup, depth 2, on by default
image input	—	not applicable
audio input / output	—	not applicable
sampling	✅	temperature, top_p, top_k, seed
context size	✅	32,768 tokens per request
concurrency	✅	4 concurrent requests
max output tokens	✅	4,096 (preset max_tokens)

Correctness

gate	description	result
kernel_tests	Unit tests of the generated kernels against reference implementations	✅ pass (45/45) ¹
golden	llama.cpp reference recorded on the same GGUF: greedy tokens and top-5 log-probs, short prompts and 1k-32k documents	✅ pass ²
compare	Greedy output vs the llama.cpp reference, token by token; every divergence is a near-tie	✅ pass ²
vision	Image input vs llama.cpp with the same projector: identical prompt tokens, replies equal up to near-ties	— not applicable
consistency	Concurrent requests give the same output as the same requests run alone	✅ pass ²
spec	Speculative decoding on gives exactly the output of speculative decoding off	✅ pass ²
agent	Multi-turn tool-calling loop: exact prompt rendering, history reuse, valid tool calls, output vs llama.cpp	✅ pass ²
agent_think_off	The tool-calling loop with thinking off	— not applicable
sampling	temperature, top_k and seed behave as specified; first-token distribution matches llama.cpp	✅ pass ²
needle	Needle-in-a-haystack prompt at up to half the context, compared with llama.cpp; over-capacity prompt refused	✅ pass ³
needle_full	Needle-in-a-haystack prompt at the full context is served	✅ pass ²
decision	Decision answers (choice, score, noul probabilities) vs llama.cpp on the same prompts	— not applicable

• ¹ DevLab Dispatch run 42528250185, 2026-11-08; device not recorded; hrx-loom unknown.
• ² DevLab Dispatch run 42527979776, LEVEL=full, 2026-11-08; device AMD RYZEN AI MAX+ 395 w/ Radeon 8060S, AMD Radeon 8060S Graphics, Ubuntu 24.04; hrx-loom 0.1.0 (hrx-system d01d1c1).
• ³ DevLab Dispatch run 42342192972, LEVEL=full, 2026-11-07; device AMD RYZEN AI MAX+ 395 w/ Radeon 8060S, AMD Radeon 8060S Graphics, Ubuntu 24.04; hrx-loom 0.1.0 (hrx-system d01d1c1).
• Gates are the loom-benchmark correctness gates (gates.sh); a gate without a recorded run shows no evidence.

Files

• model.json / model.json.lock: the card and the pinned source files (sha256 checked by loom-fetch).
• program/*.loom, weights.loom: the generated Loom programs.
• tokenizer.json: the tokenizer.
• llm_config.json: the configuration the programs were generated from.
• info.json: the measurements, gate evidence and versions this card shows; everything else comes from the files above.
• REPORT.md: how the values above were measured: setup, commands and the value of every run.

Versions: card schema loom-card/2; loom-skills ab48a1b; hrx-loom 0.1.0 (hrx-system d01d1c1); card generator 1ed9a3e.

Source files, fetched by loom-fetch from their own repositories:

• checkpoint: bartowski/Qwen2.5-0.5B-Instruct-GGUF @ 41ba88d, Qwen2.5-0.5B-Instruct-Q4_K_M.gguf