FitMyLLM
AMD· TeraScale

AMD FireGL V8600

Running LLMs on the FireGL V8600 — the long read: which models fit at which quantisation, and the settings worth changing. · Or what a budget buys

VRAM
1 GB
Budget
Bandwidth
111.1
GB/s
Models Q4
4/498
1%
7B Q4 speed
~14
Usable
Model coverage at Q41% of all
Estimated speed· By model size at Q4

Average speeds at Q4 quantization. Actual performance varies by model architecture and context length.

3B
—
1.7GB needed
7B
—
3.9GB needed
14B
—
7.9GB needed
32B
—
18.0GB needed
70B
—
39.4GB needed
Measured rig reports

We rent the machine and time every model on it: decode, VRAM peak, concurrency, watts and cost per million tokens. Yours may already be one of them — and two are free to read in full.

See the reports →
Specifications
VRAM
1 GB
Bandwidth
111.1 GB/s
FP16 Compute
0.4 TFLOPS
TDP
159W
Memory
GDDR4
Architecture
TeraScale
Stream Processors
320
4
Fast models · >30 tok/s
Real-time chat speed
4
Usable · >10 tok/s
Comfortable for all tasks
4
Total compatible
Fit in VRAM at Q4
Don’t want to buy?

Test FireGL V8600 (or anything bigger) without committing. Pay by the second, cancel anytime.

Spin up in ~60s. Pay by the second. Cancel anytime.

Some links are affiliate links — we may earn a small commission at no extra cost to you. This helps keep FitMyLLM free and independent.

Compatible models· 4
S
Falcon-H1R Tiny 90M0.09B
Falcon·256K ctx· chat· reasoning
1097
tok/s · 54% VRAM
›
S
SmolLM2 135M0.135B
Smollm·2K ctx· chat
732
tok/s · 57% VRAM
›
S
nomic-embed-text-v1.5 100M0.14B
Embedding·8K ctx· chat
705
tok/s · 57% VRAM
›
S
GPT-2 124M0.14B
Gpt2·1K ctx· chat
705
tok/s · 57% VRAM
›
Next step

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your FireGL V8600.

What this card is worth

FireGL V8600 holds 4 of the models in our catalogue and is, in practice, a Q4_K_M card — the largest it takes is Qwen 3.5 0.8B at Q4_K_M.

Tokens/sec per $100
—
8B at Q4_K_M, so cards compare like for like
VRAM per $100
—
what memory costs on this card
The biggest it takes
Qwen 3.5 0.8B0.87B · Q4_K_M0.9 GB55 tok/sest
LFM2 700M0.74B · Q4_K_M0.9 GB61 tok/sest
Falcon-H1R Tiny 0.6B0.6B · Q6_K0.9 GB58 tok/sest
Falcon Perception 0.6B0.6B · Q5_K_S0.9 GB66 tok/sest
Falcon-H1 0.5B0.52B · Q6_K0.8 GB65 tok/sest
Qwen 2.5 0.5B0.5B · Q8_00.9 GB55 tok/sest
SmolVLM 500M0.5B · Q6_K0.9 GB68 tok/sest
SmolLM2 360M0.36B · Q8_00.8 GB73 tok/sest
Against cards of similar memory
M2 (8GB)5 GB$5992.8 tok/s per $100
M3 (8GB)5 GB$5992.8 tok/s per $100
M1 (8GB)5 GB$4992.2 tok/s per $100
Radeon RX 6600S4 GB$175—
FireGL V86001 GB——

Neighbours in memory rather than in price: memory decides whether a card can do the job at all, so two cards of the same size at different prices is the comparison you are making. Ordered by memory, then bandwidth — not by the value column, which is worked out from bandwidth and price alone and therefore rewards a cheap card whatever its software stack does to that bandwidth in practice. Read it as one input, not as a ranking.

Device under test

AMD FireGL V8600 — 1 GB VRAM.

FireGL V8600 spec
Brand
AMD
VRAM
1 GB GDDR4
Bandwidth
111.1 GB/s
FP16 Compute
0.4 TFLOPS
FP32 Compute
0.4 TFLOPS
Stream Processors
320
TDP
159 W
Architecture
TeraScale
AI capability
4/ 498 models @ Q4

With 1 GB VRAM and 111.1 GB/s bandwidth, this GPU handles models up to 0.14B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~13 tok/s.

Top models for FireGL V8600
4 fit · showing 4
ModelSizeVRAM Q4tok/sAvg
nomic-embed-text-v1.5 100M0.14B0.6 GB70548.0
GPT-2 124M0.14B0.6 GB7056.5
SmolLM2 135M0.135B0.6 GB7327.0
Falcon-H1R Tiny 90M0.09B0.5 GB1097—